Advanced driver assistance systems (ADAS) are being developed for more and more complicated application scenarios, such that collision avoidance systems require more predictive strategies with better understanding of driving environment. Taking traffic vehicles’ maneuvers into account can greatly expand the beforehand time span of danger awareness. This paper describes a maneuver-based strategy to vehicle-to-vehicle collision threat assessment. First, a maneuver-based trajectory prediction model (MBTPM) is built in which near-future trajectories of ego vehicle and traffic vehicles are estimated with the combination of vehicle’s maneuvers and kinematic models that corresponds to every maneuver. The most probable maneuvers of ego vehicle and each traffic vehicles are modeled and inferred via Hidden Markov Models with mixture of Gaussians outputs (GMHMM). Based on the inferred maneuvers, trajectory sets consisting of vehicles’ position and motion states are predicted by kinematic models. Subsequently, time to collision (TTC) is calculated in a strategy of employing collision detection at every predicted trajectory instance. For this purpose, safe area bounding boxes are applied on every vehicle, and Separating Axis Theorem (SAT) is applied during collision detection, so that TTC calculation can conduct with both speed and accuracy. Finally, a threat index based on reverse TTC is used to quantize every traffic vehicle’s collision threat degree to ego vehicle, as well as providing a basis of desired braking actuator actions. Authentic data collected in field tests are used in algorithm training, and overall strategy is validated on PanoSim and dSPACE Simulator. Simulation result shows that MBTPM can identify e maneuvers in high accuracy rate, so that effective prediction trajectories can be generated. TTC and threat index can be calculated timely. The proposed threat assessment strategy can not only assist collision avoidance systems to deliver effective brake action, but also eliminate false alarm in certain extent.